標(biāo)題: Titlebook: Neural-Symbolic Learning and Reasoning; 18th International C Tarek R. Besold,Artur d’Avila Garcez,Benedikt Wagn Conference proceedings 2024 [打印本頁] 作者: 瘦削 時(shí)間: 2025-3-21 16:56
書目名稱Neural-Symbolic Learning and Reasoning影響因子(影響力)
書目名稱Neural-Symbolic Learning and Reasoning影響因子(影響力)學(xué)科排名
書目名稱Neural-Symbolic Learning and Reasoning網(wǎng)絡(luò)公開度
書目名稱Neural-Symbolic Learning and Reasoning網(wǎng)絡(luò)公開度學(xué)科排名
書目名稱Neural-Symbolic Learning and Reasoning被引頻次
書目名稱Neural-Symbolic Learning and Reasoning被引頻次學(xué)科排名
書目名稱Neural-Symbolic Learning and Reasoning年度引用
書目名稱Neural-Symbolic Learning and Reasoning年度引用學(xué)科排名
書目名稱Neural-Symbolic Learning and Reasoning讀者反饋
書目名稱Neural-Symbolic Learning and Reasoning讀者反饋學(xué)科排名
作者: 脆弱吧 時(shí)間: 2025-3-21 23:16 作者: BILE 時(shí)間: 2025-3-22 02:16 作者: 溝通 時(shí)間: 2025-3-22 08:06 作者: 不愿 時(shí)間: 2025-3-22 09:17
Towards Understanding the?Impact of?Graph Structure on?Knowledge Graph Embeddingsthodologies for producing KGs, which?span notions of expressivity, and are tailored for different use-cases and domains. Now, as neurosymbolic methods rise in prominence, it?is important to understand how the development of KGs according?to these methodologies impact downstream tasks, such as link p作者: 刺耳 時(shí)間: 2025-3-22 14:49 作者: mortuary 時(shí)間: 2025-3-22 19:49
Metacognitive AI: Framework and?the?Case for?a?Neurosymbolic Approachgy. In this position paper,?we examine the concept of applying metacognition to artificial intelligence. We introduce a framework for understanding metacognitive artificial intelligence (AI) that we call TRAP: transparency, reasoning, adaptation, and perception. We discuss each of these aspects in-t作者: Maximize 時(shí)間: 2025-3-22 21:56
Enhancing Logical Tensor Networks: Integrating Uninorm-Based Fuzzy Operators for?Complex Reasoning between t-norms and t-conorms,?offer unparalleled flexibility and adaptability, making them ideal?for modeling the complex, often ambiguous relationships inherent?in real-world data. By embedding these operators into Logic Tensor Networks, we present a methodology that significantly increases?the n作者: 脊椎動(dòng)物 時(shí)間: 2025-3-23 03:37
Parameter Learning Using Approximate Model Counting these hybrid models, these methods use a knowledge compiler to turn the symbolic model into a differentiable arithmetic circuit, after which gradient descent can be performed. However, these methods require compiling a reasonably sized circuit, which is not always possible, as for many symbolic pro作者: 分開 時(shí)間: 2025-3-23 08:51
Large-Scale Knowledge Integration for?Enhanced Molecular Property Predictionitical for advancements?in drug discovery and materials science. While recent work?has primarily focused on data-driven approaches, the KANO?model introduces a novel paradigm by incorporating knowledge-enhanced pre-training. In this work, we expand upon KANO by integrating?the large-scale ChEBI know作者: Pandemic 時(shí)間: 2025-3-23 12:01 作者: Ovulation 時(shí)間: 2025-3-23 16:13
On the?Value of?Labeled Data and?Symbolic Methods for?Hidden Neuron Activation Analysistional Neural Network. Our approach uses?a Wikipedia-derived concept hierarchy with approx. 2 million classes as background knowledge, and deductive reasoning based Concept Induction for explanation generation. Additionally, we explore?and compare the capabilities of off-the-shelf pre-trained multim作者: 細(xì)胞膜 時(shí)間: 2025-3-23 22:00
Concept Induction Using LLMs: A?User Experiment for?Assessmentraditional post-hoc algorithms, while useful, often struggle to deliver interpretable explanations. Concept-based models offer a promising avenue by incorporating explicit representations of concepts to enhance interpretability. However, existing research on automatic concept discovery methods?is of作者: Fester 時(shí)間: 2025-3-24 01:25
Error-Margin Analysis for?Hidden Neuron Activation Labelsence. While existing literature in explainable AI emphasizes the importance of labeling neurons with concepts to understand their functioning, they mostly focus on identifying what stimulus activates a neuron in most cases; this corresponds to the notion of . in information retrieval. We argue that 作者: Kernel 時(shí)間: 2025-3-24 03:49
LENs for?Analyzing the?Quality of?Life of?People with?Intellectual Disabilityintellectual disability and uses?a framework in the literature of neurosymbolic AI, specifically?the family of interpretable DL named logic explained networks,?to provide explanations for the predictions. By integrating explainability, our research enhances the richness of?the predictions and qualit作者: vitreous-humor 時(shí)間: 2025-3-24 08:08
ECATS: Explainable-by-Design Concept-Based Anomaly Detection for?Time Seriestion. However, the complexity inherent in Cyber Physical Systems (CPS) creates a challenge when it comes?to explainability methods. To overcome this inherent lack?of interpretability, we propose ECATS, a concept-based neuro-symbolic architecture where concepts are represented as Signal Temporal?Logi作者: dura-mater 時(shí)間: 2025-3-24 14:21 作者: amygdala 時(shí)間: 2025-3-24 14:56 作者: outrage 時(shí)間: 2025-3-24 21:45
e writing of the present book: Almost every topic that we taughtrequiredsomeskillsinalgebra,andinparticular,computeral- bra! From positioning to transformation problems inherent in geodesy and geoinformatics, knowledge of algebra and application of computer algebra software were required. In prepari作者: AGATE 時(shí)間: 2025-3-25 02:12
Conference proceedings 2024celona, Spain during September 9-12th, 2024...The 30 full papers and 18 short papers were carefully reviewed and selected from 89 submissions, which presented the latest and ongoing research work on neurosymbolic AI.?Neurosymbolic AI aims to build rich computational models and systems by combining n作者: Narcissist 時(shí)間: 2025-3-25 03:50 作者: 碎片 時(shí)間: 2025-3-25 10:42
Towards Understanding the?Impact of?Graph Structure on?Knowledge Graph Embeddingsrediction using KG embeddings (KGE). In this paper, we modify FB15k-237?in several ways (e.g., by increasingly including semantic metadata). This significantly changes the graph structure (e.g., centrality). We assess how these changes impact the link prediction task,?using six KGE models.作者: 暖昧關(guān)系 時(shí)間: 2025-3-25 15:23 作者: immunity 時(shí)間: 2025-3-25 18:14
Logic Supervised Learning for?Time Series - Continual Learning for?Appliance Detectionters implausible results out which is helpful?for productive usage, on the other hand these post processed results?can be used to retrain the network and adapt it for a specific household in a continual learning process.作者: 果仁 時(shí)間: 2025-3-25 20:58 作者: 痛恨 時(shí)間: 2025-3-26 03:50 作者: Delirium 時(shí)間: 2025-3-26 06:38 作者: 輕率看法 時(shí)間: 2025-3-26 10:10 作者: Charade 時(shí)間: 2025-3-26 15:07 作者: Myosin 時(shí)間: 2025-3-26 17:53 作者: 領(lǐng)帶 時(shí)間: 2025-3-26 22:37 作者: 令人不快 時(shí)間: 2025-3-27 02:21
Bringing Back Semantics to?Knowledge Graph Embeddings: An Interpretability Approachach?to derive interpretable vector spaces with human-understandable dimensions in terms of the features of the entities. We demonstrate the efficacy of . in encapsulating desired semantic features, presenting evaluations both in the vector?space as well as in terms of semantic similarity measurements.作者: Cleave 時(shí)間: 2025-3-27 08:35
Conference proceedings 2024resented the latest and ongoing research work on neurosymbolic AI.?Neurosymbolic AI aims to build rich computational models and systems by combining neural and symbolic learning and reasoning paradigms. This combination hopes to form synergies among their strengths while overcoming their.complementary weaknesses..作者: Gullible 時(shí)間: 2025-3-27 09:54
0302-9743 eld in Barcelona, Spain during September 9-12th, 2024...The 30 full papers and 18 short papers were carefully reviewed and selected from 89 submissions, which presented the latest and ongoing research work on neurosymbolic AI.?Neurosymbolic AI aims to build rich computational models and systems by c作者: 違抗 時(shí)間: 2025-3-27 14:56
Large-Scale Knowledge Integration for?Enhanced Molecular Property Prediction 9 out of?14 molecular property prediction datasets. This highlights?the importance of utilizing a larger and more diverse set of functional groups to enhance molecular representations for property predictions.作者: 你不公正 時(shí)間: 2025-3-27 21:20 作者: debacle 時(shí)間: 2025-3-28 01:59 作者: 撫育 時(shí)間: 2025-3-28 04:28
978-3-031-71169-5The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerl作者: GRAVE 時(shí)間: 2025-3-28 08:10 作者: 包裹 時(shí)間: 2025-3-28 11:21 作者: 消耗 時(shí)間: 2025-3-28 16:07
Zuzanna Gawrysiak,Agata ?ywot,Agnieszka ?awrynowicz作者: 暫時(shí)休息 時(shí)間: 2025-3-28 20:48
Andrew Eells,Brandon Dave,Pascal Hitzler,Cogan Shimizu作者: 炸壞 時(shí)間: 2025-3-29 01:52
Hua Wei,Paulo Shakarian,Christian Lebiere,Bruce Draper,Nikhil Krishnaswamy,Sergei Nirenburg作者: BILIO 時(shí)間: 2025-3-29 05:20 作者: anarchist 時(shí)間: 2025-3-29 09:06
Abhilekha Dalal,Rushrukh Rayan,Adrita Barua,Eugene Y. Vasserman,Md Kamruzzaman Sarker,Pascal Hitzler作者: 尖牙 時(shí)間: 2025-3-29 11:51
Irene Ferfoglia,Gaia Saveri,Laura Nenzi,Luca Bortolussi作者: Leisureliness 時(shí)間: 2025-3-29 16:59
Antoine Domingues,Nitisha Jain,Albert Mero?o Pe?uela,Elena Simperl作者: defray 時(shí)間: 2025-3-29 21:09 作者: Truculent 時(shí)間: 2025-3-30 02:16 作者: 厭倦嗎你 時(shí)間: 2025-3-30 07:43
Enhancing Neuro-Symbolic Integration with?Focal Loss: A Study on?Logic Tensor Networks on?an object detection benchmark show that the focal logLTN aggregator achieves higher performance and stability than its standard counterpart, with potential application in many other practical scenarios.作者: 故意 時(shí)間: 2025-3-30 10:12
Enhancing Logical Tensor Networks: Integrating Uninorm-Based Fuzzy Operators for?Complex Reasoningway for?more sophisticated artificial intelligence systems. This work lays?a foundational stone for future research in the intersection of?fuzzy logic and neural-symbolic computing, suggesting directions?for further exploration and integration of fuzzy systems elements?into Logic Tensor Networks.. h作者: grounded 時(shí)間: 2025-3-30 13:14
Parameter Learning Using Approximate Model Countingsing approximation allows more complex queries to be compiled and our experiments show that their addition helps reduce the training loss. However, we observe that there is a limit to the addition of partial circuits after which there is no more improvement.作者: 最初 時(shí)間: 2025-3-30 19:10 作者: FEAS 時(shí)間: 2025-3-30 23:28
Concept Induction Using LLMs: A?User Experiment for?Assessmentavailable in the data via prompting to facilitate this process.?To evaluate the output, we compare the concepts generated by the?LLM with two other methods: concepts generated by humans and the?ECII heuristic concept induction system. Since there is no established metric to determine the human under作者: Yourself 時(shí)間: 2025-3-31 03:49 作者: Inveterate 時(shí)間: 2025-3-31 07:22
9樓作者: 按時(shí)間順序 時(shí)間: 2025-3-31 10:48
9樓作者: 桶去微染 時(shí)間: 2025-3-31 16:26
10樓作者: 訓(xùn)誡 時(shí)間: 2025-3-31 21:12
10樓作者: 向前變橢圓 時(shí)間: 2025-3-31 23:05
10樓作者: 倔強(qiáng)一點(diǎn) 時(shí)間: 2025-4-1 03:58
10樓
